kongxin cee54cdd49
fix(web-fetch): stop sending .env.example placeholder keys to providers (#8206)
* fix(web-fetch): stop sending .env.example placeholder keys to providers

make config and make setup copy .env.example into .env, and the template
set nine search/fetch provider keys to example values such as
JINA_API_KEY=your-jina-api-key. The default keyless Jina Reader sent
that text as a Bearer key, so every web_fetch on a fresh install failed
with 401 while make doctor reported web fetch as configured.

- .env.example comments those nine lines out, like every other credential
  in the template already is.
- provider_credentials.resolve_api_key reads a your-...-key/-token/-secret
  value as unset, so existing .env files that still hold the placeholders
  recover without editing, for every provider that resolves keys there.

* chore: leave the changelog entry to merge time

Per CONTRIBUTING.md (#8202), maintainers add changelog entries when they
merge a pull request.

* fix(web-search): route every provider key and doctor through one placeholder rule

Review follow-up for #8206:

- provider_credentials exposes is_template_placeholder(), the single
  definition of an .env.example example value. key/token/secret must be
  a whole hyphen-separated word, so a real value such as your-monkey or
  your-passkey is no longer dropped.
- Serper, Serply, Sofya, SpecStream, Unbrowse, Webz, Brave, Tencent WSA
  and You.com resolve config and environment keys through
  resolve_api_key instead of private strip-and-send copies, so an old
  .env that still holds the template value no longer sends it.
- make doctor asks the same predicate: a placeholder key is reported as
  still holding the .env.example value instead of "set", and a literal
  placeholder in config.yaml falls back to the environment key as the
  runtime does.
- A census test keeps credential environment reads under community/
  wrapped in resolve_api_key.

* fix(web-search): match shipped placeholders exactly and mirror Browserless precedence in doctor

Second review follow-up for #8206:

- is_template_placeholder() matches exactly the your-... values that
  .env.example ships instead of a pattern, so a token an operator chose
  (a self-hosted Browserless TOKEN such as your-review-team-token) is
  sent again. A test keeps the set equal to the template.
- make doctor mirrors Browserless: a configured token field is
  authoritative, blank or not, and BROWSERLESS_TOKEN is read only when
  the field is omitted. A blank or placeholder token now warns instead
  of reporting the variable, cross-checked against the client.
- The keyless Jina and You.com providers stay ok but name JINA_API_KEY
  or YDC_API_KEY when a placeholder there is ignored, and a literal
  placeholder api_key in config.yaml is named when no env key backs it.

* fix(doctor): match each web provider's key precedence; drop the dead Jina api_key from docs

Found while re-checking #8206 against every provider's runtime:

- Browserless used as web_fetch had no doctor key check; it now gets the
  same authoritative token handling as web_capture.
- InfoQuest reads only INFOQUEST_API_KEY, so doctor no longer counts an
  api_key field in its tool config as configured.
- GroundRoute needs a key for every call but had no doctor entry, so a
  missing key reported ok.
- You.com names a placeholder api_key in config that it ignores.
- The Jina web_fetch docs snippet carried api_key: $JINA_API_KEY, which
  the tool never reads. With JINA_API_KEY now commented out in
  .env.example, that line made config loading fail on a fresh install.
- The provider_credentials docstring now scopes doctor's use of the
  predicate to web provider keys, and the scripts guide no longer says
  .env.example ships live placeholder keys.
2026-11-13 23:23:29 +08:00

192 lines
8.1 KiB
Python

"""
Web search and fetch tools powered by SpecStream.
SpecStream is a live web data engine with a Search API and an Extract API.
Search answers a question from the live web and returns the search results it
read, ranked, with a direct answer when the sources agree on one. Fetch returns
the main text of a page, PDF, Word or Excel file as markdown. An API key is
required. Sign up at https://specstream.ai to get one.
"""
import json
import logging
import os
import httpx
from langchain.tools import tool
from deerflow.community.provider_credentials import resolve_api_key
from deerflow.community.search_max_results import coerce_max_results
from deerflow.community.url_safety import safe_public_result_url
from deerflow.config import get_app_config
logger = logging.getLogger(__name__)
_SPECSTREAM_BASE_URL = "https://api.specstream.ai"
_SPECSTREAM_SEARCH_PATH = "/v1/web-search"
_SPECSTREAM_EXTRACT_PATH = "/v1/extract"
# The search API takes a question of 1 to 2000 characters.
_SPECSTREAM_MAX_QUERY_CHARS = 2000
# Each fetched URL gets up to 30 seconds on the SpecStream side.
_SPECSTREAM_TIMEOUT = 60
_SPECSTREAM_FETCH_MAX_CHARS = 4096
_api_key_warned: set[str] = set()
def _get_api_key(tool_name: str) -> str | None:
config = get_app_config().get_tool_config(tool_name)
configured = resolve_api_key(config.model_extra.get("api_key")) if config is not None else None
return configured or resolve_api_key(os.getenv("SPECSTREAM_API_KEY"))
def _missing_key_message(tool_name: str) -> str:
if tool_name not in _api_key_warned:
_api_key_warned.add(tool_name)
logger.warning("SpecStream API key is not set for '%s'. Set SPECSTREAM_API_KEY in your environment or provide api_key in config.yaml. Sign up at https://specstream.ai", tool_name)
return "SPECSTREAM_API_KEY is not configured"
def _specstream_request(method: str, path: str, api_key: str, *, params: dict | None = None, payload: dict | None = None) -> tuple[dict | None, str | None]:
"""Send a request to a SpecStream endpoint.
Returns a ``(data, error)`` tuple: on success ``data`` is the object inside
the response's ``data`` envelope and ``error`` is ``None``; on failure
``data`` is ``None`` and ``error`` is a message the caller can hand back to
the model.
"""
headers = {"Authorization": f"Bearer {api_key}"}
try:
with httpx.Client(timeout=_SPECSTREAM_TIMEOUT) as client:
response = client.request(method, f"{_SPECSTREAM_BASE_URL}{path}", headers=headers, params=params, json=payload)
response.raise_for_status()
body = response.json()
except httpx.HTTPStatusError as e:
logger.error("SpecStream API returned HTTP %s: %s", e.response.status_code, (e.response.text or "")[:500])
return None, f"SpecStream API error: HTTP {e.response.status_code}"
except Exception as e:
logger.error("SpecStream request failed: %s: %s", type(e).__name__, str(e)[:500])
return None, str(e)[:500]
data = body.get("data") if isinstance(body, dict) else None
if not isinstance(data, dict):
logger.error("SpecStream returned an unexpected payload type: %s", type(body).__name__)
return None, "SpecStream returned an unexpected response format"
return data, None
def _response_objects(data: dict, container: str) -> list[dict] | None:
"""Return the object entries of a SpecStream response container, or None if malformed.
A missing or null container is empty. A non-list container, or a non-empty
list holding no objects, is malformed: the caller reports a format error
rather than "No results found", which would tell the agent the query
legitimately matched nothing.
"""
value = data.get(container)
if value is None:
return []
if not isinstance(value, list):
logger.error("SpecStream returned an unexpected '%s' payload type: %s", container, type(value).__name__)
return None
usable = [item for item in value if isinstance(item, dict)]
if value and not usable:
logger.error("SpecStream returned '%s' with no usable result objects", container)
return None
return usable
def _normalize_answer(answer: object) -> dict | None:
"""Keep the direct answer with the page it was read from, or None when there is none."""
if not isinstance(answer, dict) or not answer.get("value"):
return None
return {
"value": answer.get("value"),
"url": safe_public_result_url(answer.get("page")),
}
@tool("web_search", parse_docstring=True)
def web_search_tool(query: str, max_results: int | None = None) -> str:
"""Search the web for information. Use this tool to find current information, news, articles, and facts from the internet.
Args:
query: Search keywords or a question describing what you want to find. Be specific for better results.
max_results: Maximum number of results to return. If omitted, uses the configured value (default 5).
"""
config = get_app_config().get_tool_config("web_search")
config_extra = (config.model_extra or {}) if config is not None else {}
# Honor the caller-supplied max_results; fall back to config only when omitted.
if max_results is None:
max_results = config_extra.get("max_results")
max_results = coerce_max_results(max_results, provider="SpecStream", logger=logger)
api_key = _get_api_key("web_search")
if not api_key:
return json.dumps({"error": _missing_key_message("web_search"), "query": query}, ensure_ascii=False)
data, error = _specstream_request("GET", _SPECSTREAM_SEARCH_PATH, api_key, params={"q": query.strip()[:_SPECSTREAM_MAX_QUERY_CHARS]})
if error is not None:
return json.dumps({"error": error, "query": query}, ensure_ascii=False)
sources = _response_objects(data, "sources")
if sources is None:
return json.dumps({"error": "SpecStream returned an unexpected response format", "query": query}, ensure_ascii=False)
answer = _normalize_answer(data.get("answer"))
if not sources and answer is None:
return json.dumps({"error": "No results found", "query": query}, ensure_ascii=False)
output: dict[str, object] = {"query": query}
if answer is not None:
output["answer"] = answer
results = [
{
"title": source.get("title") or "",
"url": safe_public_result_url(source.get("url")),
"snippet": source.get("snippet") or "",
}
for source in sources[:max_results]
]
output["total_results"] = len(results)
output["results"] = results
return json.dumps(output, indent=2, ensure_ascii=False)
@tool("web_fetch", parse_docstring=True)
def web_fetch_tool(url: str) -> str:
"""Fetch the contents of a web page at a given URL.
Only fetch EXACT URLs that have been provided directly by the user or have been returned in results from the web_search and web_fetch tools.
This tool can NOT access content that requires authentication, such as private Google Docs or pages behind login walls.
Do NOT add www. to URLs that do NOT have them.
URLs must include the schema: https://example.com is a valid URL while example.com is an invalid URL.
Args:
url: The URL to fetch the contents of.
"""
api_key = _get_api_key("web_fetch")
if not api_key:
return f"Error: {_missing_key_message('web_fetch')}"
data, error = _specstream_request("POST", _SPECSTREAM_EXTRACT_PATH, api_key, payload={"urls": [url], "format": "markdown"})
if error is not None:
return f"Error: {error}"
results = _response_objects(data, "results")
if results is None:
return "Error: SpecStream returned an unexpected response format"
if not results:
return "Error: No results found"
result = results[0]
status = result.get("status")
if status != "ok":
return f"Error: SpecStream could not read the page ({status or 'unknown status'})"
content = result.get("text")
content = content[:_SPECSTREAM_FETCH_MAX_CHARS] if isinstance(content, str) else ""
if not content:
return "Error: No content found"
title = result.get("title") or "Untitled"
return f"# {title}\n\n{content}"